利用 onnxruntime 及 PaddleOCR 提供的模型, 对图片中的文字进行检测与识别.
Project description
PPOCR-ONNX
简介
利用 onnxruntime 及 PaddleOCR 提供的模型, 对图片中的文字进行检测与识别.
使用模型
- 文字检测:
ch_PP-OCRv3_det_infer
- 方向分类:
cls mobile v2
- 文字识别:
ch_PP-OCRv2_rec_infer
参考
- PaddleOCR
- 手把手教你使用ONNXRunTime部署PP-OCR
ch_PP-OCRv3_det_infer
及ch_PP-OCRv2_rec_infer
模型来自 RapidAI/RapidOCR
安装
pip install ppocr-onnx
使用
from ppocronnx.predict_system import TextSystem
import cv2
text_sys = TextSystem()
# 识别单行文本
res = text_sys.ocr_single_line(cv2.imread('single_line_text.png'))
print(res)
# 批量识别单行文本
res = text_sys.ocr_lines([cv2.imread('single_line_text.png')])
print(res[0])
# 检测并识别文本
img = cv2.imread('test.png')
res = text_sys.detect_and_ocr(img)
for boxed_result in res:
print("{}, {:.3f}".format(boxed_result.ocr_text, boxed_result.score))
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
ppocr-onnx-0.0.3.7.tar.gz
(10.5 MB
view details)
Built Distribution
File details
Details for the file ppocr-onnx-0.0.3.7.tar.gz
.
File metadata
- Download URL: ppocr-onnx-0.0.3.7.tar.gz
- Upload date:
- Size: 10.5 MB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/3.7.1 importlib_metadata/4.10.0 pkginfo/1.8.2 requests/2.27.1 requests-toolbelt/0.9.1 tqdm/4.62.3 CPython/3.9.8
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | 21dd334aaa2920fc0690dc4f28a530f84bbea9d4c1543a4515e208163d617ca4 |
|
MD5 | 8f5aba230bbfa5fec5348b8282e3ad37 |
|
BLAKE2b-256 | efd54570ba6ad27c6ac00ad1f50a5dc6507851cbac865a298b85e8205387875c |
File details
Details for the file ppocr_onnx-0.0.3.7-py3-none-any.whl
.
File metadata
- Download URL: ppocr_onnx-0.0.3.7-py3-none-any.whl
- Upload date:
- Size: 10.5 MB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/3.7.1 importlib_metadata/4.10.0 pkginfo/1.8.2 requests/2.27.1 requests-toolbelt/0.9.1 tqdm/4.62.3 CPython/3.9.8
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | ea993f38843afc4406ff6a737c7c2a22a1dbccfe6cc1a4174fac68e9d1e36fc0 |
|
MD5 | f60afbe50e9c760ade0146ac92c8dd44 |
|
BLAKE2b-256 | 7bd3c5cffde848c23165fab9b4759d34854df8c4380edec1c64f4ce7ae1f0db4 |